GitHub·Code·MIT

X-iZhang/CCD

[ACL 2026] 📷 CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding — A flexible, plug-and-play toolkit for various radiology MLLM backbones, further boosting overall performance

14 stars·Updated Jun 2026
chest-xrayscontrastive-decodinghallucination-mitigationmcp-servermedical-image-analysisminimum-viable-productmultimodal-large-language-modelsradiology-report-generationvisual-question-answering
Open on GitHub

Authors

Repository owner

Linked papers

Code

CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding

iclr · 2026

Why Lacuna links this resource
Repository names this paper

<!-- Add logo here --> <h1 align="center"> <img src="./assets/CCD_icon_logo.png" alt="CCD Logo" height="27" style="position: relative; top: -2px;"/> <strong>CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding</strong> </h1> <div align="center"> <a href="https://git.io/typing-svg"> <img src="https://readme-typing-svg.demolab.com?font=Fira+Code&pause=1000&center=true&width=500&lines=Training-free%2C+decode+smart.;Think+clinically%2C+act+precisely.;Powered+by+Clinica

README:focal_exact_title·Open evidence